删除选项集
AI agents call deleteOptionset to permanently remove resources in MCP Mingdao — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs an irreversible deletion operation on option sets (enumerated lists/dropdowns used in forms/databases). Deletion of such data cannot be undone and affects the data structure. This is Destructive rather than Write because deletions are permanent and non-reversible.
From the tool's definition Tool name is 'deleteOptionset' and description '删除选项集' translates to 'delete option set'. The action is irreversible deletion of configuration data.
Attacks that exploit this kind of access
删除选项集. It is categorised as a Destructive tool in the MCP Mingdao MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Mingdao MCP server in PolicyLayer and add a rule for deleteOptionset: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCP Mingdao. Nothing to install.
deleteOptionset is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the deleteOptionset rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for deleteOptionset. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
deleteOptionset is provided by the MCP Mingdao MCP server (mingdaocloud/mcp-mingdao). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →